Multi-Agent Reinforcement Learning for SLA-Aware Network Slicing in UAV-Enabled MEC

TRUAV: Distributed Multi-Agent Reinforcement Learning for Trajectory Planning and Routing Enhancement in UAV-Aided IoT-Enabled VANETs

Unmanned aerial vehicles (UAVs) have emerged as a key enabler of next-generation Internet of Things (IoT) ecosystems, offering flexible aerial relaying to extend connectivity across dynamic vehicular ad hoc networks (VANETs) in smart city environments. However, conventional centralized approaches for UAV trajectory planning require continuous global network state aggregation, making them impractical under bandwidth and energy constraints typical of dense urban deployments. In this article, we present TRUAV, a distributed multi-agent reinforcement learning framework based on independent tabular Q-learning for joint UAV trajectory planning and routing enhancement in UAV-aided VANETs. Each UAV is equipped with a local Q-learning agent that operates purely on locally observable information, including vehicle density, packet queue states, and neighbor UAV positions, thereby eliminating the need for global state exchange. A potential-game-inspired reward design encourages spatial diversity and routing-aware UAV positioning among interacting agents while accounting for energy consumption. Numerical simulations over a large urban area with 200 mobile vehicles show that the proposed TRUAV framework achieves network coverage and packet delivery ratios comparable to centralized deep reinforcement learning methods, while also improving relay delay and energy efficiency. Finally, we discuss emerging challenges and future research directions for distributed multi-agent UAV-assisted IoT systems.

SkySched: A Hierarchical and Scalable Reinforcement Learning Framework for Multi-UAV Vehicular Edge Computing Network

Unmanned Aerial Vehicles (UAVs) are increasingly deployed as embodied aerial agents in low-altitude economies, forming mobile aerial edge networks that enable flexible computation offloading for vehicles. However, their limited endurance and frequent join/leave behaviours result in highly dynamic topologies, undermining long-term resource availability. Moreover, existing vehicle-centric task scheduling strategies cause resource contention and decision complexity in dense environments. To address these challenges, this paper proposes a hierarchical and scalable reinforcement learning-based scheduling framework (SkySched). In SkySched, UAVs collaboratively make deployment and task scheduling decisions. The framework consists of two tightly coupled modules. First, an adaptive UAV deployment module introduces a capability encoding mechanism that compresses heterogeneous UAV attributes into a unified one-dimensional capability index. This compact representation enables a Scalable Proximal Policy Optimization (SPPO) algorithm to efficiently coordinate UAV positioning, maximizing task coverage and sustaining network-wide computing availability under dynamic topology variations. Second, a hierarchical task scheduling module is designed, where K-means-based Roadside Unit (RSU) clustering enables vertical task offloading, while a SPPO-driven horizontal UAV-to-UAV task redistribution mechanism achieves fine-grained load balancing across the UAV swarm. Simulations demonstrate that SkySched consistently outperforms state-of-the-art methods in terms of task coverage and load fairness, validating its effectiveness as an agentic AI-driven embodied networking solution for UAV-assisted vehicular edge computing.

AoI Minimization in Multi-UAV Edge Computing via Influence-Aware Heterogeneous Federated Multiagent Reinforcement Learning

Collaborative Trajectory and Resource Optimization in Multi-UAV MEC Under Jamming: An LLM-Guided MARL Framework

Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) systems provide flexible computing services for resource-constrained devices, but malicious jamming attacks introduce dynamic channel conditions and resource competition, making joint trajectory and resource optimization challenging. This paper investigates this problem in multi-UAV MEC systems under jamming, aiming to minimize delay and energy consumption while ensuring anti-jamming robustness. The problem is formulated as a decentralized partially observable Markov decision process (Dec-POMDP). However, traditional multi-agent reinforcement learning (MARL) approaches struggle with high exploration costs and low sampling efficiency in high-dimensional hybrid action spaces. To overcome these limitations, we propose an LLM-guided MARL framework instantiated with the multi-agent deep deterministic policy gradient (MADDPG), which leverages LLM-generated semantic trajectory prompts to dynamically constrain exploration within the continuous action space, effectively compressing the policy search space and accelerating convergence. Simulation results demonstrate that the proposed method achieves $3.4\times $ to $5\times $ faster convergence over hierarchical MADDPG, MADDPG, and independent soft actor-critic (ISAC) baselines, significantly reducing training costs while maintaining superior performance and anti-jamming robustness.

Toward Low-Delay and Energy-Efficient UAV-Assisted MEC Systems Through Intelligent Resource Allocation

A Prioritized Adaptive Weighting based on Deep Deterministic Policy Gradient (PAW-DDPG) as an enhanced Deep Deterministic Policy Gradient (DDPG) algorithm to minimize both processing delay and energy consumption by jointly optimizing user scheduling, partial-task offloading, and UAV trajectory is proposed.

Energy-Aware Multi-UAV Collaboration for Data Collection and Trajectory Planning With MADDPG

Unmanned Aerial Vehicles (UAVs) are pivotal for facilitating data collection in emergency scenarios. Despite the potential of Multi-Agent Deep Reinforcement Learning (MADRL) in coordinating such systems, existing researches struggle to resolve the high-dimensional coupling of data collection, trajectory planning, and energy scheduling under strict collision avoidance and Return-To-Base (RTB) constraints. This paper proposes a energy-aware cooperative MADRL framework designed to maximize data collection utility under energy constraints. Specifically, we employ a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) approach featuring a Centralized Training with Decentralized Execution (CTDE) design and a multi-objective reward mechanism to balance conflicting optimization goals. Extensive simulations validate the advantages of the proposed framework over leading baselines. Notably, the algorithm exhibits significant quantitative advantages in complex high-load scenarios. These outcomes prove that our method achieves higher task completion rates while strictly adhering to RTB and safety protocols.